What is OmicsClaw CLAUDE.md?

Repository instructions for OmicsClaw, an AI platform for analyzing biological data such as genes, proteins, and metabolites. It requires answers to follow documented methods or script results instead of guesses.

Use them to route biology questions to the appropriate analysis skill, maintain the repository, follow its issue process, and verify changes against project documentation.

They make scientific responses traceable and give developers a repeatable process for maintenance, debugging, refactoring, and verification.

How TianGzlab/OmicsClaw configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to TianGzlab/OmicsClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/TianGzlab/OmicsClaw/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/TianGzlab/OmicsClaw

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tiangzlab/omicsclaw/claude-md/github.svg)](https://agentmods.dev/instructions/tiangzlab/omicsclaw/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tiangzlab/omicsclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/tiangzlab/omicsclaw/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tiangzlab/omicsclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/tiangzlab/omicsclaw/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 598 This file is loaded in full into every session.

When invoked 598 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00598	$0.00598
Opus 5.5	$0.00239	$0.00239
Sonnet 5.5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 29d ago against content hash 59d78905f38d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

OmicsClaw CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — OmicsClaw repository

OMICSCLAW.md is the runtime contract of the OmicsClaw analysis agent: omicsclaw/entry/assembly.py puts it at the top of that agent's system prompt, followed by SAFETY_RULES and TOOL_GUIDANCE from the same module. Read it when a change affects what that agent is told, and when adding or removing a skill (its routing table and counts there are kept by hand).

Repository Maintenance Contract

When you are acting on repository maintenance, refactoring, or other developer-facing tasks rather than end-user omics analysis:

Read README.md for what the project is and CHANGELOG.md for recent decisions and milestones.
Then read root SPEC.md and AGENTS.md.
Reply in the user's language and stay concise and execution-focused.
Use a concise plan, root-cause debugging, focused tests, and verification evidence for non-trivial repository changes.
When you make an important repository decision or complete a milestone, add an entry at the top of CHANGELOG.md. Change README.md only when a user-facing entry point, install step or headline feature changes; its What's New holds at most five items of one sentence each.
Run the humanizer skill (.claude/skills/humanizer/SKILL.md) in embedded mode over prose you write: code comments, docstrings, docs, plans, README text, commit messages and PR descriptions. Keep code, commands, paths and identifiers unchanged.

Agent skills

Issue tracker

Issues and PRDs live in GitHub Issues for zhou-1314/OmicsClaw. Use the gh CLI (gh issue create|view|list|comment|edit|close), and infer the repository from the current clone unless a command needs an explicit --repo zhou-1314/OmicsClaw. "Publish to the issue tracker" means create an issue; "fetch the relevant ticket" means read its body, labels and comments.

Triage labels

Five canonical roles, each mapping to the GitHub label of the same name:

Label	Meaning
`needs-triage`	A maintainer must evaluate the issue.
`needs-info`	More information is required from the reporter.
`ready-for-agent`	Fully specified and safe for an AFK agent.
`ready-for-human`	Requires human implementation or judgement.
`wontfix`	Will not be actioned.

Read the full file on GitHub · 53 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

29d ago Changed · -310 lines · -3,747 tokens per session 59d78905f38d
2mo ago First seen · 363 lines · 4,345 tokens per session scan A dab8a8196745

Subscribe to this mod's changes

OmicsClaw CLAUDE.md is an instructions file published in the GitHub repository TianGzlab/OmicsClaw (161 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 598 tokens to every session, about $0.0024 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Single-Cell bioinformatics knowledge-graph llm-agent multi-agents multi-omics

OmicsClaw CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
OmicsClaw CLAUDE.mdTianGzlab/OmicsClaw	Instructions file	161	1mo ago	Apache-2.0	A	598	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

OmicsClaw: Instructions file for Claude Code